Ensemble techniques are a powerful approach to creating better decision makers in
machine learning. Multiple decision makers are trained to solve a given task, grouped in an …

In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved
tasks can allow agents to quickly solve new problems. In some cases, these new problems …

The success of reinforcement learning in a variety of challenging sequential decision-
making problems has been much discussed, but often ignored in this discussion is the …

Exploration is a key problem in reinforcement learning, since agents can only learn from
data they acquire in the environment. With that in mind, maintaining a population of agents is …

We study the problem of reward shaping to accelerate the training process of a
reinforcement learning agent. Existing works have considered a number of different reward …

Discovering achievements with a hierarchical structure in procedurally generated
environments presents a significant challenge. This requires an agent to possess a broad …

Multi-objective problems with correlated objectives are a class of problems that deserve
specific attention. In contrast to typical multi-objective problems, they do not require the …

To make reinforcement learning algorithms run in a reasonable amount of time, it is
frequently necessary to use a well-chosen reward function that gives appropriate “hints” to …

We present a modular approach to reinforcement learning that uses a Bayesian
representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set) …

In complex reinforcement learning (RL) problems, policies with similar rewards may have
substantially different behaviors. It remains a fundamental challenge to optimize rewards …